# Universal Assisted Generation: Faster Decoding with Any Assistant Model

DevFeed: [Universal Assisted Generation: Faster Decoding with Any Assistant Model](<https://devfeed.tech/articles/universal-assisted-generation-faster-decoding-with-any-assistant-model-7546.md>)

Original publisher: [Read original article](<https://huggingface.co/blog/universal_assisted_generation>)

Author: Daniel Korat; Oren Pereg; Moshe Berchansky; Jonathan Mamou; Joao Gante; Lewis Tunstall; Nadav Timor; Moshe Wasserblat

Published: 2024-10-29T00:00:00Z

Content type: article

Language: en

Sources: [Hugging Face - Blog](<https://devfeed.tech/sources/hugging-face-blog.md>)

Topics: [Inference](<https://devfeed.tech/topics/inference.md>), [Latency](<https://devfeed.tech/topics/latency.md>), [text-generation](<https://devfeed.tech/topics/text-generation.md>), [LLMs](<https://devfeed.tech/topics/llms.md>), [hugging face](<https://devfeed.tech/topics/hugging-face.md>), [intel](<https://devfeed.tech/topics/intel.md>)

Tags: [collaboration](<https://devfeed.tech/tags/collaboration.md>), [hugging-face](<https://devfeed.tech/tags/hugging-face.md>), [inference](<https://devfeed.tech/tags/inference.md>), [intel](<https://devfeed.tech/tags/intel.md>), [latency](<https://devfeed.tech/tags/latency.md>), [nlp](<https://devfeed.tech/tags/nlp.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [research](<https://devfeed.tech/tags/research.md>), [text-generation](<https://devfeed.tech/tags/text-generation.md>)

## AI overview

This article explains Universal Assisted Generation, a technique that accelerates large language model text generation by using a smaller assistant model to propose tokens and a target model to verify them. The approach extends assisted generation to pairs of models with different tokenizers and can provide 1.5x-3x speedups depending on the task and models used.

## Source excerpt

We're on a journey to advance and democratize artificial intelligence through open source and open science.